efficientdet_d2(pretrained: bool = False, overrides: object = {})EfficientDet-D2 ().
Compound-scaled variant: EfficientNet-B2 backbone, BiFPN 112 channels with 5 repeats, head depth 3, 768x768 input. Approximately 8.1M parameters; COCO test-dev mAP of 43.0% (paper Table 2).
Model Size
Parameters
pretrainedbool= FalseReserved for future pretrained-weight loading. Currently ignored.
**overridesobject= {}Keyword overrides forwarded into
EfficientDetConfig.Returns
EfficientDetForObjectDetectionDetector with the D2 configuration applied.
Notes
See Tan et al., 2020 (arXiv:1911.09070), Table 2.
Examples
>>> import lucid
>>> from lucid.models.vision.efficientdet import efficientdet_d2
>>> model = efficientdet_d2()
>>> x = lucid.randn(1, 3, 768, 768)
>>> out = model(x)
>>> out.pred_boxes.shape[-1]
4